Maxim G Sharaev

Maxim G Sharaev
Skolkovo Institute of Science and Technology | Skoltech · Center for Computational and Data-Intensive Science and Engineering

PhD

About

79
Publications
13,204
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
435
Citations
Citations since 2017
70 Research Items
425 Citations
2017201820192020202120222023020406080100120
2017201820192020202120222023020406080100120
2017201820192020202120222023020406080100120
2017201820192020202120222023020406080100120

Publications

Publications (79)
Article
Full-text available
The purpose of this paper was to study causal relationships between left and right hippocampal regions (LHIP and RHIP, respectively) within the default mode network (DMN) as represented by its key structures: the medial prefrontal cortex (MPFC), posterior cingulate cortex (PCC), and the inferior parietal cortex of left (LIPC) and right (RIPC) hemis...
Preprint
Full-text available
Rett Syndrome (RS) is a rare neurodevelopmeтtal disorder characterized by mutations in the MECP2 gene. Patients with RS have severe motor abnormalities and are often unable to walk, use hands and speak. The preservation of perceptual and cognitive functions is hard to assess, while clinicians and care-givers point out that these patients need more...
Article
Clinical analysis of EEG is time-consuming and requires a high level of expertise. In this study, we developed a new approach for EEG analysis applying quantitative methods for assessing clinical indices of EEG for four age groups of children with severe autism spectrum disorder (ASD) and four age- and non-verbal IQ-matched groups of typically deve...
Article
Full-text available
BACKGROUND: Recent studies have shown that SARS-CoV-2 can have neuropsychiatric consequences and has the ability to penetrate the blood-brain barrier. If SARS-CoV-2 has a specific route of entry into the brain, it may leave imprints in the form of specific changes in brain morphology. Older individuals are most vulnerable to the neuropsychiatric CO...
Article
Full-text available
A constant blood supply to the brain is required for mental function. Research with Doppler ultrasonography has important clinical value and burgeoning potential with machine learning applications in studies predicting gestational age and vascular aging. Critically, studies on ultrasound metrics in school-age children are sparse and no machine lear...
Article
Full-text available
Nuclear functional magnetic resonance imaging (fMRI) is one of the most popular methods for studying the functional activity of the human brain. In particular, this method is used in medicine to obtain information about the state of the functional networks of the patient’s brain. However, the process of processing and analysis of experimental fMRI...
Chapter
Since 2012 the BraTS competition has become a benchmark for brain MRI segmentation. The top-ranked solutions from the competition leaderboard of past years are primarily heavy and sophisticated ensembles of deep neural networks. The complexity of the proposed solutions can restrict their clinical use due to the long execution time and complicate th...
Article
Objective: To develop a system for preoperative prediction of individual activations of motor and speech areas in patients with brain gliomas using resting state fMRI (rsfMRI), task-based fMRI (tb-fMRI), direct cortical stimulation and machine learning methods. Material and methods: Thirty-three patients with gliomas (19 females and 14 males age...
Article
Objective: To analyze and compare the results of cerebral cortex mapping with task-based (tb-fMRI) and resting-state functional MRI in patients with glioma of eloquent cortical areas. Material and methods: There were 55 patients (24 men and 31 women aged 24 - 74 years, median 39) with glial tumors. In 26 patients, the tumor was located in motor...
Article
Full-text available
Independent Component Analysis (ICA) is a conventional approach to exclude non-brain signals such as eye movements and muscle artifacts from electroencephalography (EEG). A rejection of independent components (ICs) is usually performed in semiautomatic mode and requires experts’ involvement. As also revealed by our study, experts’ opinions about th...
Article
Predicting accuracy in cognitively challenging tasks has potential applications in education and industry. Task demand has been linked with increases in response time and variations in reaction time and eye-tracking metrics, however, machine learning research has not been used to predict performance on tasks with multiple levels of difficulty. We r...
Chapter
In the current work we focused on the problem of identifying the mechanism of interaction of neural networks in the human brain in cognitive processes. An important step in solving this problem is to identify functionally homogeneous regions of the brain. In this paper, we present two methods which are needed to identify these regions and build map...
Chapter
Focal cortical dysplasia (FCD) is one of the most common epileptogenic lesions associated with cortical development malformations. However, the accurate detection of the FCD relies on the radiologist professionalism, and in many cases, the lesion could be missed. In this work, we solve the problem of automatic identification of FCD on magnetic reso...
Preprint
Full-text available
Independent Component Analysis (ICA) is a conventional approach to exclude non-brain signals such as eye-movements and muscle artifacts from electroencephalography (EEG). Due to other possible EEG contaminations, a rejection of independent components (ICs) is usually performed in semiautomatic mode and requires experts’ involvement. Noteworthy, as...
Chapter
Deep learning shows high potential for many medical image analysis tasks. Neural networks can work with full-size data without extensive preprocessing and feature generation and, thus, information loss. Recent work has shown that the morphological difference in specific brain regions can be found on MRI with the means of Convolution Neural Networks...
Chapter
Despite the importance of experimental confirmation, the ability of wide range of brain mapping methods to discover brain cognitive architectures in most studies can’t be evaluated directly. Only in rare cases, when due to medical need, it is possible to conduct experiments during neurosurgical operations, is it possible to assess the accuracy of c...
Chapter
In this work, we compared many different methods proposed for calculating the functional interaction of brain regions based on resting-state fMRI data. We compared them according to the criterion of the stability of the results to small changes in the parameters of both the methods themselves and the input data including different levels of noise....
Article
Full-text available
Reward processing is a fundamental human activity. The basal ganglia are recognized for their role in reward processes; however, specific roles of the different nuclei (e.g., nucleus accumbens, caudate, putamen and globus pallidus) remain unclear. Using quantitative meta-analyses we assessed whole-brain and basal ganglia specific contributions to m...
Preprint
Full-text available
Focal cortical dysplasia (FCD) is one of the most common epileptogenic lesions associated with cortical development malformations. However, the accurate detection of the FCD relies on the radiologist professionalism, and in many cases, the lesion could be missed. In this work, we solve the problem of automatic identification of FCD on magnetic reso...
Preprint
Full-text available
Machine learning and computer vision methods are showing good performance in medical imagery analysis. Yetonly a few applications are now in clinical use and one of the reasons for that is poor transferability of themodels to data from different sources or acquisition domains. Development of new methods and algorithms forthe transfer of training an...
Preprint
Full-text available
ABIDE is the largest open-source autism spectrum disorder database with both fMRI data and full phenotype description. These data were extensively studied based on functional connectivity analysis as well as with deep learning on raw data, with top models accuracy close to 75\% for separate scanning sites. Yet there is still a problem of models tra...
Preprint
Full-text available
Deep learning shows high potential for many medical image analysis tasks. Neural networks work with full-size data without extensive preprocessing and feature generation and, thus, information loss. Recent work has shown that morphological difference between specific brain regions can be found on MRI with deep learning techniques. We consider the p...
Preprint
In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics. We present a review of brain imaging-based neurolinguistic studies with a focus on the natural language representations, such as word embeddings and pre-trained language models. Mutual enrichment of neurolinguistics and language te...
Article
Full-text available
In this paper, our focus is the connection and influence of language technologies on the research in neurolinguistics. We present a review of brain imaging-based neurolinguistic studies with a focus on the natural language representations, such as word embeddings and pre-trained language models. Mutual enrichment of neurolinguistics and language te...
Article
Full-text available
The view that the left cerebral hemisphere in humans "dominates" over the "subdominant" right hemisphere has been so deeply entrenched in neuropsychology that no amount of evidence seems able to overcome it. In this article, we examine inhibitory cause-and-effect connectivity among human brain structures related to different parts of the triune evo...
Article
Full-text available
In region of interest (ROI) brain analysis, the proper selection of voxels in ROIs plays a crucial role. In existing methods for selection of functionally homogeneous regions of human brain based on fMRI data, each voxel is attributed to some brain region, not taking into account the possibility of the existence of borderline voxels demonstrating t...
Article
Maximum resection and preservation of neurological function are main principles in surgery of brain tumors, especially glial neoplasms with diffuse growth. Therefore, exact localizing of eloquent brain areas is an important component in surgical planning ensuring optimal resection with minimal postoperative neurological deficit. Functional MRI is u...
Article
Full-text available
Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level l...
Preprint
Full-text available
Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolutional deep neural network layers for MRI data classification. We propose new 3D deformable convolutions(d-convolutions), implement them in VoxResNet architecture and apply for structural...
Preprint
Segmentation of tumors in brain MRI images is a challenging task, where most recent methods demand large volumes of data with pixel-level annotations, which are generally costly to obtain. In contrast, image-level annotations, where only the presence of lesion is marked, are generally cheap, generated in far larger volumes compared to pixel-level l...
Article
Full-text available
Deep learning convolutional neural networks have proved to be a powerful tool for MRI analysis. In current work, we explore the potential of the deformable convolution deep neural network layers for MRI data classification. We propose new 3D deformable convolutions (d-convolutions), implement them in VoxResNet architecture and apply for structural...
Chapter
In this work, we aimed at predicting children’s fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health. The target variable was regressed on a data collection site, sociodemographic variables, and brain volume, thus being independent to the potentially informative f...
Article
Here we present our answers to a critical commentary by Elkhonon Goldberg on our recent publication (Velichkovsky et al., 2018). To avoid discussions about novelty effects in the human brain activity and memory processes, we narrowed down this response to a reanalysis of our data along the lines proposed in the commentary, namely to comparing the e...
Conference Paper
Full-text available
Background We aimed at searching for a reliable method to separate patients with Major Depressive Disorder (MDD) from healthy controls (HC). The biomarkers, if found in resting-state EEG, may become cheap and easy-to-use tools for medical diagnostic. While some authors report positive findings on this matter (Henriques, 1991), the results are still...
Conference Paper
Full-text available
In this work, we aim at predicting children's fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health. The target variable was regressed on a data collection site, sociodemographic variables and brain volume, thus being independent to the potentially informative fact...
Preprint
Full-text available
In this work, we aim at predicting children's fluid intelligence scores based on structural T1-weighted MR images from the largest long-term study of brain development and child health. The target variable was regressed on a data collection site, socio-demographic variables and brain volume, thus being independent to the potentially informative fac...
Article
Today, functional magnetic resonance imaging (fMRI) allows to plan surgery based on the topography of functionally important areas of the human brain cortex and tumor. This method can complement the surgical strategy with significant clinical information. The stimulus-dependent fMRI with motor and language paradigms is generally used for preoperati...
Conference Paper
Full-text available
It has long been known that patients with depression exhibit abnormal brain functional connectivity patterns, that are often studied from a graph-theoretic perspective. However, while certain simpler graph features have been examined, little has been done in the direction of advanced feature learning methodologies such as network embeddings. Our wo...
Conference Paper
Full-text available
In current work we propose a three-step approach to automatic and efficient functional brain areas mapping as well demonstrate in case studies on three patients with gliomas the potential applicability of constrained source separation technique (semiblind Independent Component Analysis, ICA) to brain networks discovery and the similarity of task-ba...
Conference Paper
Full-text available
In the field of psychoneurology, analysis of neuroimaging data aimed at extracting distinctive patterns of pathologies, such as epilepsy and depression, is well known to represent a challenging problem. As the resolution and acquisition rates of modern medical scanners rise, the need to automatically capture complex spatiotemporal patterns in large...
Conference Paper
Full-text available
In the present work, we study the candidate biomarkers for the depression disorder and the depression + epilepsy comorbidity. Building on the advanced data analysis pipeline, we identify candidate biomarkers, compare them across tasks and to the previous research. The classification performance achieved by our system compares favourably to the one...
Chapter
Full-text available
As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression. Systematic research into these mental disorders increasingly involves...
Article
Full-text available
As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnos-tics, characterization, and treatment outcome prediction for psychiatric and neu-rological disorders, for instance, epilepsy and depression. Systematic research into these mental disorders increasingly involve...
Article
By taking into account Bruce Bridgeman's interest in an evolutionary framing of human cognition, we examine effective (cause-and-effect) connectivity among cortical structures related to different parts of the triune phylogenetic stratification: archicortex, paleocortex and neocortex. Using resting-state functional magnetic resonance imaging data f...
Preprint
Full-text available
As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression. Systematic research into these mental disorders increasingly involves...
Preprint
Full-text available
We consider a problem of diagnostic pattern recognition/classification from neuroimaging data. We propose a common data analysis pipeline for neuroimaging-based diagnostic classification problems using various ML algorithms and processing toolboxes for brain imaging. We illustrate the pipeline application by discovering new biomarkers for diagnosti...
Conference Paper
Full-text available
We consider a problem of diagnostic pattern recognition/classification from neuroimaging data. We propose a common data analysis pipeline for neuroimaging-based diagnostic classification problems using various ML algorithms and processing toolboxes for brain imaging. We illustrate the pipeline application by discovering new biomarkers for diagnosti...
Conference Paper
Full-text available
As machine learning continues to gain momentum in the neuroscience community, we witness the emergence of novel applications such as diagnostics, characterization, and treatment outcome prediction for psychiatric and neurological disorders, for instance, epilepsy and depression. Systematic research into these mental disorders increasingly involves...
Article
Full-text available
The performance of the human brain depends on how effectively its distinct regions communicate, especially the regions which are more strongly connected to each other than to other regions, or so called “rich-clubs”. The aim of the current work is to find a connectivity pattern between the three brain rich-club regions without any a priori assumpti...
Article
Full-text available
In animal experiments, radial traveling waves are recorded on the surface of the cortex. Our calculations show that the recording of such waves by microelectrode matrices in humans allows us to observe only their fragments. We assumed that the source of the EEG and MEG in the alpha and beta bands are radial traveling waves. Similar waves are genera...
Article
Full-text available
Ideas about relationships between "I", egocentric spatial orientation and the sense of bodily "Self " date back to work by classics of philosophy and psychology. Cognitive neuroscience has provided knowledge about brain areas involved in self-referential processing, such as the rostral prefrontal, temporal and parietal cortices, often active as par...
Article
Full-text available
Objectives Patients with major depressive disorder (MDD) show attention bias to the negative emotional stimuli. We aimed at studying the EEG-correlates of unconscious expectation of angry human faces in MDD patients compared to healthy controls. Methods 128-channel EEG was recorded in MDD (23 female and 7 male) and in healthy volunteers (22 female...
Article
Full-text available
Introduction The knowledge on brain mechanisms of psychopathology can be very useful for the diagnosis and treatment of patients. Objectives Patients with major depressive disorder (MDD) show attention bias to the negative emotional stimuli. Automatic (unconscious) emotional processing in such patients may become a prospective biomarker for depres...
Article
Full-text available
As adults we solve problems by applying our executive know-how and directing our mental-attention to relevant information. When we are not problem solving, our mind is free to wonder to things like lunchtime; this is often referred to as the default-mode. It is established that for adults the relation among executive and default-mode brain areas is...
Article
Full-text available
Study Objective: In patients with recurrent depression (hereafter "patients"), to investigate their specific neurophysiological characteristics associated with their unconscious expectation of seeing threatening visual information compared to those characteristics associated with their expectation of neutral visual stimuli. Materials and Methods: T...